AI by Hand ✍️

AI by Hand ✍️

Truncation

Crossing out the oldest turns

Prof. Tom Yeh's avatar
Prof. Tom Yeh
Aug 19, 2026
∙ Paid

Library › Context Problems

  1. The Context Window

  2. Window Occupancy

  3. Growth per Turn

  4. Remaining Space

  5. Turn Budget

  6. Retrieval Footprint

  7. Retrieval per Turn

  8. Search Rounds

  9. Window Sizing

  10. Truncation

  11. Compaction

  12. The Compaction Bill

  13. Compacted Retrieval

  14. The Compaction Threshold

  15. Verbatim Tail

  16. Stateless API

  17. Retrieval Cost

  18. Context Tax

  19. Quadratic Cost

  20. Cost Forecast

Truncation is the crudest fix for a full window: cross out the earliest turns until the new message has room. It is cheap and it always works, which is why agents do it, and it costs the beginning of the conversation, which is usually the part that said what the conversation was for. Turns go whole. You cannot drop half a turn, so the count always rounds up and a little more is thrown away than strictly had to be.

Paid members: the worksheet and its printable PDF are below ↓

This post is for paid subscribers

Already a paid subscriber? Sign in
© 2026 Tom Yeh · Privacy ∙ Terms ∙ Collection notice
Start your SubstackGet the app
Substack is the home for great culture